柯南：基于多尺度视觉证据的渐进式侦探推理学习

摘要

视频推理需进行跨帧的多步推演，这始终是多模态大语言模型面临的主要挑战。基于强化学习的方法虽能增强推理能力，但常依赖纯文本推理链导致结论缺乏事实依据或出现幻觉。相比之下，帧检索方法虽引入视觉依据，却仍受限于证据定位不准的困境。为此，我们提出Conan框架，通过证据锚定实现多步视频推理。该框架能识别上下文帧与证据帧，基于跨帧线索进行推理，并自适应决定终止推理或继续探索。为实现这一目标，我们（1）构建了Conan-91K大规模数据集，其中自动生成的推理轨迹包含帧识别、证据推理与行动决策；（2）设计了多阶段渐进式冷启动策略，结合"识别-推理-行动"强化学习视频推理训练框架，共同提升多步视觉推理能力。在六个多步推理基准测试上的大量实验表明，Conan相较基线模型Qwen2.5-VL-7B-Instruct平均准确率提升超10%，达到业界最优水平。此外，Conan在长视频理解任务中展现出色泛化能力，验证了其强大的可扩展性与鲁棒性。

English

Video reasoning, which requires multi-step deduction across frames, remains a major challenge for multimodal large language models (MLLMs). While reinforcement learning (RL)-based methods enhance reasoning capabilities, they often rely on text-only chains that yield ungrounded or hallucinated conclusions. Conversely, frame-retrieval approaches introduce visual grounding but still struggle with inaccurate evidence localization. To address these challenges, we present Conan, a framework for evidence-grounded multi-step video reasoning. Conan identifies contextual and evidence frames, reasons over cross-frame clues, and adaptively decides when to conclude or explore further. To achieve this, we (1) construct Conan-91K, a large-scale dataset of automatically generated reasoning traces that includes frame identification, evidence reasoning, and action decision, and (2) design a multi-stage progressive cold-start strategy combined with an Identification-Reasoning-Action (AIR) RLVR training framework to jointly enhance multi-step visual reasoning. Extensive experiments on six multi-step reasoning benchmarks demonstrate that Conan surpasses the baseline Qwen2.5-VL-7B-Instruct by an average of over 10% in accuracy, achieving state-of-the-art performance. Furthermore, Conan generalizes effectively to long-video understanding tasks, validating its strong scalability and robustness.

柯南：基于多尺度视觉证据的渐进式侦探推理学习

Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence

摘要

Support